{"id":"W4248599979","doi":"10.32920/ryerson.14668077.v1","title":"A mapreduce relational-database index-selection tool","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Selection (genetic algorithm); Index (typography); Index selection; Task (project management); Set (abstract data type); Process (computing); Data mining; Relational database; Big data; Database; Systems engineering; Engineering; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002352355,0.0001818623,0.0001635702,0.0001120508,0.0001415977,0.0005543656,0.0008580531,0.0001665396,0.000149137],"category_scores_gemma":[0.00006461993,0.000187482,0.00008385935,0.0004092045,0.00002068571,0.0005169845,0.001968386,0.0005111826,0.00009461585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000776302,"about_ca_system_score_gemma":0.0004478291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000236061,"about_ca_topic_score_gemma":0.00002890499,"domain_scores_codex":[0.9983171,0.00004364292,0.0002872692,0.0008398606,0.0003223774,0.0001897031],"domain_scores_gemma":[0.9984072,0.00006790306,0.0001306807,0.001123843,0.0002001531,0.00007019704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004846445,0.0006662008,0.001760648,0.00016877,0.0002088292,0.00003072236,0.0009090565,0.005785133,0.001548272,0.5540395,0.07454917,0.3603289],"study_design_scores_gemma":[0.0001607752,0.00001173774,0.007314105,0.0001073692,0.00001614212,0.00004201613,0.00003484982,0.9669864,0.0009461772,0.004252612,0.01964479,0.0004830004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004581742,0.0000790558,0.9896107,0.001402197,0.0004509945,0.0002054298,0.00006264656,0.0003362967,0.003270896],"genre_scores_gemma":[0.04649291,0.00004643871,0.9475167,0.0003582435,0.0002312618,0.0002522526,0.0009770007,0.00001514891,0.004110061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9612013,"threshold_uncertainty_score":0.7645295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02981339338773392,"score_gpt":0.2702355443306068,"score_spread":0.2404221509428728,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}